Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PROPERTY
    -0.07
     Empresa
    -0.07
    _reward
    -0.06
     �
    -0.06
     Squ
    -0.06
    وم
    -0.06
    -0.06
     ROC
    -0.06
     latency
    -0.06
    aln
    -0.06
    POSITIVE LOGITS
    sono
    0.07
     weniger
    0.06
    حب
    0.06
     نفت
    0.06
     نیز
    0.06
     Less
    0.06
    つの
    0.06
     reconstruct
    0.06
     سپس
    0.06
     outfile
    0.06
    Act Density 0.001%

    No Known Activations